A collection of portable, reusable and cross-platform automation recipes (CM scripts) with a human-friendly interface and minimal dependencies to make it easier to build, run, benchmark and optimize AI, ML and other applications and systems across diverse and continuously changing models, data sets, software and hardware (cloud/edge)
cm run script --tags=run-mlperf,inference,_find-performance,_full --model=sdxl --implementation=nvidia --framework=tensorrt --category=edge --test_query_count=20 -scenario=Offline --adr.cuda.version=12.4.1 --execution_mode=test --device=cuda --docker --docker_cache=no --quiet --rerun -j
Output:
1452.5 rclone sync 'https://developer.download.nvidia.com/compute/cuda/12.4.1/local_installers/cuda_12.4.1_550.54.15_linux.run' '/home/cmuser/CM/repos/local/cache/24e8e1b481ee448c/cuda_12.4.1_550.54.15_linux.run' -P
1452.5 2024/07/02 23:38:21 Failed to create file system for "https://developer.download.nvidia.com/compute/cuda/12.4.1/local_installers/cuda_12.4.1_550.54.15_linux.run": didn't find section in config file
1452.5 - Checking posthook dependencies on other CM scripts:
1452.5 - Checking post dependencies on other CM scripts:
1452.5 - running time of script "get,rclone": 0.01 sec.
1452.5 - Processing env after dependencies ...
1452.5 - Running preprocess ...
1452.5
1452.5 Downloading from https://developer.download.nvidia.com/compute/cuda/12.4.1/local_installers/cuda_12.4.1_550.54.15_linux.run
1452.5
1452.5 - Running native script "/home/cmuser/CM/repos/gateoverflow@cm4mlops/script/download-file/run.sh" from temporal script "tmp-run.sh" in "/home/cmuser/CM/repos/local/cache/24e8e1b481ee448c" ...
1452.5
1452.5 ! cd /home/cmuser/CM/repos/local/cache/24e8e1b481ee448c
1452.5 ! call /home/cmuser/CM/repos/gateoverflow@cm4mlops/script/download-file/run.sh from tmp-run.sh
1452.5
1452.5 CM error: Portable CM script failed (name = download-file, return code = 256)
To reproduce the issue:
Output: